Model comparison
Command R vs DeepSeek V4 Flash
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 31.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
Cohere
DeepSeekSummary
- They share 19 benchmarks with published results for both. Command R scores higher in 0 categories and DeepSeek V4 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 13.8.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 90.9% for DeepSeek V4 Flash.
- Both cost about the same: $0.15 input and $0.60 output per million tokens.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 128K.
Side by side
| Command R | DeepSeek V4 Flash | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 31.4 | 53.6 |
| Released | 2024-08-30 | 2026-04-24 |
| Weights | Open | Open |
| Context window | 128K | 1M |
| Max output | 4K | 393K |
| Input $ / M tokens | $0.15 | $0.15 |
| Output $ / M tokens | $0.60 | $0.60 |
| Results tracked | 29 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
Command R: 29.3 (#306), DeepSeek V4 Flash: 47.9 (#59)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Coding | 1169 | 1457 |
| FrontierCode | — | 18.8% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 49.9% |
| WeirdML | — | 63% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| ALE-Bench | — | 1,306 |
Reasoning DeepSeek V4 Flash leads
Command R: 13.8 (#331), DeepSeek V4 Flash: 53.7 (#30)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1444 |
| DTBench | 46.4% | 90.9% |
| LMCA | 9.2% | 41.7% |
| ARC-AGI-2 | — | 61.4% |
| SimpleBench | — | 61.1% |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 89.6% |
| ARC-AGI-1 | — | 89% |
| CritPt | — | 16.6% |
| Chess Puzzles | — | 33% |
| LiveBench Reasoning | 21.9% | — |
| Mystery Game Puzzles | — | 34% |
| LiveBench Data Analysis | 33.3% | — |
| Epoch Capabilities Index | — | 154.49 |
| LiveBench | 27.5% | — |
Math DeepSeek V4 Flash leads
Command R: 28.0 (#246), DeepSeek V4 Flash: 60.3 (#37)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Math | 1155 | 1427 |
| FrontierMath (Tiers 1-3) | — | 57.5% |
| FrontierMath Tier 4 | — | 24.4% |
| MathArena Final-Answer Competitions | — | 76.5% |
| OTIS Mock AIME 2024-2025 | — | 94.4% |
| ProofBench | — | 56% |
| LiveBench Math | 19.4% | — |
Knowledge DeepSeek V4 Flash leads
Command R: 31.0 (#221), DeepSeek V4 Flash: 55.4 (#48)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Expert | 1138 | 1441 |
| GPQA Diamond | — | 91% |
| SimpleQA Verified | — | 33.6% |
| MMLU | 65.2% | — |
Multilingual DeepSeek V4 Flash leads
Command R: 35.7 (#245), DeepSeek V4 Flash: 53.0 (#72)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | 1174 | 1420 |
| LMArena Chinese | 1182 | 1468 |
| LMArena French | 1162 | 1439 |
| LMArena German | 1176 | 1418 |
| LMArena Japanese | 1143 | 1406 |
| LMArena Korean | 1163 | 1384 |
| LMArena Russian | 1174 | 1428 |
| LMArena Spanish | 1151 | 1436 |
Instruction Following DeepSeek V4 Flash leads
Command R: 58.1 (#261), DeepSeek V4 Flash: 74.9 (#81)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | 1167 | 1421 |
| LiveBench Instruction Following | 55.6% | — |
Long Context DeepSeek V4 Flash leads
Command R: 36.3 (#231), DeepSeek V4 Flash: 43.8 (#85)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | 1198 | 1434 |
Writing & Preference DeepSeek V4 Flash leads
Command R: 38.2 (#254), DeepSeek V4 Flash: 63.8 (#61)
| Benchmark | Command R | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | 1187 | 1432 |
| LMArena Creative Writing | 1170 | 1403 |
| LMArena Multi-Turn | 1163 | 1449 |
| EQ-Bench Creative Writing | — | 1559 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than DeepSeek V4 Flash?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 31.4 on the Noometry Index.
Which is cheaper, Command R or DeepSeek V4 Flash?
DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Command R lists at $0.15 and $0.60.
Is Command R or DeepSeek V4 Flash better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Flash does, with 1M tokens against 128K.
How many benchmarks do Command R and DeepSeek V4 Flash share?
19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek V4 Flash has 41.